© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1489
    Prev
    Next
    INDEX
    Explanations

    prefixing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļéĥ¨åĪĨ
    -0.25
    è¿ĩ渡
    -0.24
    çŃĶ
    -0.23
    åħħ
    -0.23
    è¿Ļç±»
    -0.23
    edata
    -0.22
    亮
    -0.21
    PMC
    -0.21
    满满
    -0.20
    {@
    -0.20
    POSITIVE LOGITS
    ihar
    0.26
     Nicholson
    0.23
     discipline
    0.21
    friend
    0.20
     amusement
    0.20
    ç»Ĭ
    0.20
     dist
    0.20
    formance
    0.20
    ĪæĿĥ
    0.20
    EndPoint
    0.20
    Activations Density 0.093%

    No Known Activations